Mystery: examining a crime scene

Bad Writing Habits

Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.

0-shot Creative writingRule following

Performance Score Distribution (Top 20)

Click a model name to view its detail page.

Rank	Model	Avg. Cost	Avg. Time	Stability	# 1	# 2	# 3	# 4	# 5	Total
41	GPT-5	$0.073	3.0m	89%	95	93	92	92	90	92%
1	GPT-5 Mini	$0.0099	40.3s	90%	93	92	91	91	91	92%
32	GPT-5.2	$0.060	1.6m	88%	94	93	92	89	88	91%
30	GPT-5.1	$0.063	1.5m	89%	92	91	91	91	89	91%
39	Claude Opus 4.6	$0.077	1.3m	87%	94	92	92	88	87	91%
52	Qwen 3.5 397B A17B	$0.044	5.8m	89%	92	91	90	90	90	91%
2	Mistral Large	$0.013	35.0s	85%	92	91	89	88	87	89%
14	GPT-4.1	$0.018	40.9s	81%	94	93	88	85	84	89%
4	Z.AI GLM 5	$0.0079	1.1m	85%	91	89	89	89	84	88%
5	Rocinante 12B	$0.0006	25.4s	80%	95	90	88	85	83	88%
7	MoonshotAI: Kimi K2.5	$0.012	1.0m	83%	93	90	89	84	84	88%
29	Claude Sonnet 4.5	$0.029	35.7s	81%	94	91	91	82	81	88%
21	Hermes 3 405B	$0.0020	59.2s	78%	94	93	89	81	80	87%
24	o4 Mini High	$0.023	38.2s	82%	92	89	89	86	81	87%
54	Claude 3.5 Sonnet	$0.044	37.5s	72%	96	94	83	82	82	87%
13	Writer: Palmyra X5	$0.011	24.2s	81%	93	87	86	86	84	87%
6	Llama 3.1 70B	$0.0007	33.1s	83%	90	88	87	86	83	87%
10	Ministral 3B	$0.0001	1.1m	81%	91	88	86	85	84	87%
8	Z.AI GLM 4.7 Flash	$0.0020	1.3m	84%	89	87	87	86	84	87%
3	Gemini 3 Flash (Preview)	$0.0067	17.5s	84%	89	87	87	85	85	87%
18	Claude Haiku 4.5	$0.0093	20.2s	80%	89	89	88	87	78	86%
22	Mistral Large 2	$0.011	28.7s	80%	93	86	86	84	83	86%
40	Gemini 3 Pro (Preview)	$0.049	49.7s	83%	88	88	87	85	83	86%
12	Z.AI GLM 4.5	$0.0045	37.2s	82%	89	88	85	84	83	86%
19	Llama 3.1 Nemotron 70B	$0.0023	32.3s	81%	88	87	86	84	79	85%
27	Hermes 3 70B	$0.0006	31.1s	78%	90	89	84	81	80	85%
26	o4 Mini	$0.014	22.3s	81%	87	87	86	85	79	85%
33	Cohere Command R+ (Aug. 2024)	$0.016	1.3m	82%	87	87	87	83	80	85%
9	DeepSeek-V2 Chat	$0.0016	36.9s	83%	86	86	85	84	83	85%
44	Claude 3.7 Sonnet	$0.037	46.9s	81%	88	86	85	83	81	85%
43	Z.AI GLM 4.7	$0.0098	1.9m	78%	89	88	84	83	79	85%
55	Claude Opus 4.5	$0.067	56.1s	83%	86	85	85	84	83	84%
16	Qwen 3.5 Plus (2026-02-15)	$0.0051	25.8s	83%	85	85	85	85	82	84%
20	GPT-4o Mini (temp=0)	$0.0010	24.7s	81%	86	85	84	84	82	84%
11	Ministral 8B	$0.0002	9.9s	82%	86	86	85	82	82	84%
38	GPT-4o, Aug. 6th (temp=0)	$0.016	29.9s	77%	89	86	83	82	80	84%
34	Z.AI GLM 4.6	$0.0062	1.4m	80%	87	86	85	82	80	84%
46	GPT-4o, May 13th (temp=0)	$0.028	19.0s	77%	88	86	84	84	77	84%
23	Gemini 2.5 Flash	$0.0057	11.6s	81%	87	85	84	83	81	84%
17	Mistral NeMO	$0.0003	11.1s	81%	86	84	83	83	82	84%
15	GPT-4o Mini (temp=1)	$0.0011	25.2s	83%	85	84	84	83	82	84%
50	Gemini 2.5 Pro	$0.040	41.1s	79%	88	84	83	82	80	83%
25	Mistral Small Creative	$0.0006	9.8s	79%	88	86	85	81	78	83%
36	Qwen 2.5 72B	$0.0006	27.7s	75%	89	85	81	80	80	83%
28	Gemini 2.5 Flash Lite	$0.0009	11.8s	79%	85	85	82	81	81	83%
42	GPT-4o, Aug. 6th (temp=1)	$0.016	36.9s	78%	87	86	84	79	78	83%
37	WizardLM 2 8x22b	$0.0016	24.6s	75%	88	87	83	80	75	83%
45	Llama 3.1 8B	$0.0003	2.0m	78%	85	85	83	81	78	83%
31	Stealth: Aurora Alpha	$0.0000	10.4s	78%	85	82	80	–	–	82%
47	Claude Sonnet 4	$0.028	43.4s	79%	84	84	83	82	78	82%
35	Claude 3.5 Haiku	$0.0027	12.5s	78%	86	85	85	77	76	82%
51	GPT-4o, May 13th (temp=1)	$0.030	15.6s	78%	83	82	81	80	78	81%
49	GPT-4.1 Mini	$0.0027	16.6s	72%	88	80	80	77	74	80%
48	Claude 3 Haiku	$0.0020	15.6s	75%	82	80	78	78	78	79%
53	GPT-5 Nano	$0.0042	1.4m	77%	78	78	78	78	77	78%
56	GPT-4.1 Nano	$0.0006	10.5s	69%	83	82	75	74	74	78%
85.25%

Bad Writing Habits

Mystery: examining a crime scene

Performance Score Distribution (Top 20)

Price-Performance Score Distribution (Top 20)

Most Stable Models (Top 20)

Top Overall Models (Top 20)